Sheetwise Label Maker

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description goes further by disclosing what is actually performed (column detection, USPS formatting, missing-field and duplicate reporting, cleaned CSV output). The explicit exclusions — no address verification, no ZIP+4 lookup, no label printing — are exactly the kind of boundary an agent needs before promising a user an outcome.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: the usage trigger and example utterances come first, then the exclusions. Every clause carries information, though the first sentence is long and dense enough that the list of reported problems and the 'cleaned CSV download' are easy to skim past.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, fully optional, nested-input tool with an output schema present, the description covers the input modes, the processing behavior, and the boundaries; return values are correctly left to the output schema. The only thing an agent might still wonder about — limits on list size or what happens on unsupported file types — is minor and partly available in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the per-parameter descriptions already carry the detail and a baseline of 3 would be defensible. The description earns an extra point by explaining the two input modes (uploaded file vs typed list) and the automatic behaviors — heading-based column detection and USPS formatting — that the schema alone does not make obvious.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('check or clean a mailing list') plus the concrete operations: reads a CSV/XLSX or typed list, detects name/street/city/state/ZIP columns, USPS-formats addresses, and reports missing fields and duplicates. It explicitly distinguishes itself from the sibling generate_label_sheet, so an agent can route correctly without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with an explicit trigger ('use this when the user wants to check or clean a mailing list before printing labels') and backs it with three quoted user phrasings. It also names the specific alternative for the adjacent task ('does not print the labels (use generate_label_sheet)'), giving both when-to-use and when-not-to-use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/closed-world, so the description's job is to add scope and result shape; it does both by enumerating the returned layout fields (label size, columns/rows, margins, pitch, equivalent products) and the US-Letter-only universe. The only missing element is guidance on behavior when multiple filters conflict or return nothing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the use case, then scope exclusions and the sibling reference — no filler sentences. The long run of quoted example queries is useful for matching but is the one portion that could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, all-optional-parameter lookup with a full output schema, the description covers trigger, scope boundaries, sibling handoff, and result contents. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each of the three params is already documented with examples, so the baseline is 3. The description's example queries hint that free-text phrasing is acceptable, but it adds little about how kind/query/per_sheet combine or which takes precedence.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Searches the supported US Letter label sheets by product number, label size, labels per sheet or use') plus exactly what it returns. It also explicitly separates itself from generate_label_sheet, so an agent can route without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the triggering user phrasings ('avery 5160 size', 'which labels for return address'), names the alternative tool for the printing case, and states two negative scopes (no A4 sheets, no label-maker tape). When-to-use, when-not, and the alternative are all explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behavior: output is a paginated vector PDF aligned to the label stock, with USPS address lines, shrink-to-fit fonts, start position for partly used sheets, optional alignment test page and outlines. It also discloses what is returned (preview, PDF, cleaned CSV), which is the key non-obvious trait.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the use case, then capabilities, then exclusions — a sensible order. It is long and the enumerated label-stock list and feature run-on are dense, but nearly every clause maps to an actual parameter, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 20-parameter tool with nested objects, this description covers input sources, output artifacts, layout alignment, and out-of-scope capabilities; the output schema handles return details and annotations cover safety. Nothing an agent needs in order to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic framing beyond the schema by explaining the coherent modes: typed labels vs uploaded CSV/XLSX, return-address fill mode, copies per label, and the start-position workflow for partially used sheets. It doesn't give per-parameter detail, but the capability grouping helps an agent plan the call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and artifact: builds a vector PDF label sheet that lines up with a named label layout, on US Letter. The list of supported products (5160/8160, 5161-5168, place cards, etc.) and input modes makes it unmistakably distinct from check_mailing_list and find_label_template.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with an explicit trigger sentence and a rich set of quoted user phrasings ("print address labels from excel", "start printing at label 7 on a used sheet") that map directly to invocation. Negative scope is stated (no postage, no barcodes, no nutrition labels), but it never routes to the sibling tools find_label_template or check_mailing_list, so alternatives are left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.